Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wonders
    -0.07
     худож
    -0.07
     BRAND
    -0.06
     conceived
    -0.06
    744
    -0.06
     brand
    -0.06
    repositories
    -0.06
     کودکان
    -0.06
     Jacques
    -0.06
    Handled
    -0.06
    POSITIVE LOGITS
     Firstly
    0.15
     firstly
    0.12
     Secondly
    0.11
     Lastly
    0.10
    平成
    0.08
    Lastly
    0.07
    とき
    0.07
     Lowest
    0.07
    .easy
    0.07
    .centerY
    0.07
    Act Density 0.003%

    No Known Activations